CoolFace
Modelpublic

artificialguybr/QWEN-2-1.5B-Synthia-II-Redmond

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
2likes40downloads
Model Card

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Qwen2-1.5B Fine-tuned on Synthia v1.5-II

A special thanks to Redmond.ai for sponsoring the GPU resources for this fine-tuning process.

This model is a fine-tuned version of Qwen/Qwen2-1.5B on the Synthia v1.5-II dataset, which contains over 20.7k instruction-following examples.

Model Description

Qwen2-1.5B is part of the latest Qwen2 series of large language models. The base model brings significant improvements in:

  • —Language understanding and generation
  • —Structured data processing
  • —Support for multiple languages
  • —Long context handling

This fine-tuned version enhances the base model's instruction-following capabilities through training on the Synthia v1.5-II dataset.

Model Architecture

  • —Type: Causal Language Model
  • —Parameters: 1.5B

🌐 Website

You can find more of my models, projects, and information on my official website:

  • —[artificialguy.com](https://artificialguy.com/)

🚀 Prompt Hub

Need high-quality prompts for image models and LLMs? Explore [findgoodprompt.com](https://findgoodprompt.com).

💖 Support My Work

If you find this model useful, please consider supporting my work. It helps me cover server costs and dedicate more time to new open-source projects.

Intended Uses & Limitations

This model is intended for:

  • —Instruction following and task completion
  • —Text generation and completion
  • —Conversational AI applications

The model inherits the capabilities of the base Qwen2-1.5B model, while being specifically tuned for instruction following.

Training Procedure

Training Data

The model was fine-tuned on the Synthia v1.5-II dataset containing 20.7k instruction-following examples.

Training Hyperparameters

The following hyperparameters were used during training:

  • —Learning rate: 1e-05
  • —Train batch size: 5
  • —Eval batch size: 5
  • —Seed: 42
  • —Gradient accumulation steps: 8
  • —Total train batch size: 40
  • —Optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —LR scheduler type: cosine
  • —LR scheduler warmup steps: 100
  • —Number of epochs: 3
  • —Sequence length: 4096
  • —Sample packing: enabled
  • —Pad to sequence length: enabled

Framework Versions

  • —Transformers 4.45.0.dev0
  • —Pytorch 2.3.1+cu121
  • —Datasets 2.21.0
  • —Tokenizers 0.19.1

<details><summary>See axolotl config</summary>

axolotl version: 0.4.1

<!-- artificialguybr-links:start -->

Explore More

Discover more of my models, projects, and practical AI resources:

  • —AI tools directory: JustGoodAI — a curated directory of useful AI tools.

<!-- artificialguybr-links:end -->